Conference paper Open Access

A Case Study of Closed-Domain Response Suggestion with Limited Training Data

Galke, Lukas; Gerstenkorn, Gunnar; Scherp, Ansgar


JSON-LD (schema.org) Export

{
  "inLanguage": {
    "alternateName": "eng", 
    "@type": "Language", 
    "name": "English"
  }, 
  "description": "<p>We analyze the problem of response suggestion in a closed domain along a real-world scenario of a digital library. We present a text-processing pipeline to generate question-answer pairs from chat transcripts. On this limited amount of training data, we compare retrieval-based, conditioned-generation, and dedicated representation learning approaches for response suggestion. Our results show that retrieval-based methods that strive to find similar, known contexts are preferable over parametric approaches from the conditioned-generation family, when the training data is limited. We, however, identify a specific representation learning approach that is competitive to the retrieval-based approaches despite the training data limitation.</p>", 
  "license": "http://creativecommons.org/licenses/by/4.0/legalcode", 
  "creator": [
    {
      "affiliation": "Kiel University", 
      "@id": "https://orcid.org/0000-0001-6124-1092", 
      "@type": "Person", 
      "name": "Galke, Lukas"
    }, 
    {
      "affiliation": "University of Potsdam", 
      "@id": "https://orcid.org/0000-0002-4889-511X", 
      "@type": "Person", 
      "name": "Gerstenkorn, Gunnar"
    }, 
    {
      "affiliation": "University of Stirling", 
      "@id": "https://orcid.org/0000-0002-2653-9245", 
      "@type": "Person", 
      "name": "Scherp, Ansgar"
    }
  ], 
  "url": "https://zenodo.org/record/2583130", 
  "image": "https://zenodo.org/static/img/logos/zenodo-gradient-round.svg", 
  "datePublished": "2018-09-06", 
  "headline": "A Case Study of Closed-Domain Response Suggestion with Limited Training Data", 
  "keywords": [
    "conversational agents", 
    "neural networks", 
    "representation learning"
  ], 
  "@context": "https://schema.org/", 
  "identifier": "https://doi.org/10.1007/978-3-319-99133-7_18", 
  "@id": "https://doi.org/10.1007/978-3-319-99133-7_18", 
  "@type": "ScholarlyArticle", 
  "name": "A Case Study of Closed-Domain Response Suggestion with Limited Training Data"
}
17
20
views
downloads
Views 17
Downloads 20
Data volume 4.7 MB
Unique views 15
Unique downloads 18

Share

Cite as